WO2022247203A1 - 自动驾驶车辆的控制方法、装置、设备以及存储介质 - Google Patents

自动驾驶车辆的控制方法、装置、设备以及存储介质 Download PDF

Info

Publication number
WO2022247203A1
WO2022247203A1 PCT/CN2021/135073 CN2021135073W WO2022247203A1 WO 2022247203 A1 WO2022247203 A1 WO 2022247203A1 CN 2021135073 W CN2021135073 W CN 2021135073W WO 2022247203 A1 WO2022247203 A1 WO 2022247203A1
Authority
WO
WIPO (PCT)
Prior art keywords
acceleration
vehicle
pitch angle
corrected
current
Prior art date
Application number
PCT/CN2021/135073
Other languages
English (en)
French (fr)
Inventor
王泽旭
庄登祥
薛晶晶
Original Assignee
阿波罗智能技术(北京)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 阿波罗智能技术(北京)有限公司 filed Critical 阿波罗智能技术(北京)有限公司
Publication of WO2022247203A1 publication Critical patent/WO2022247203A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/11—Pitch movement
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/107—Longitudinal acceleration
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B60W2520/105—Longitudinal acceleration
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/16—Pitch

Definitions

  • the embodiments of the present disclosure relate to the computer field, specifically to the field of artificial intelligence technology such as automatic driving and intelligent transportation, and in particular to a control method, device, device, and storage medium for an automatic driving vehicle.
  • Self-driving vehicles can rely on the cooperation of artificial intelligence, visual computing, radar, monitoring devices, etc., so that the on-board computer can automatically and safely control the self-driving vehicle without any human operation.
  • the control module is an important module for the self-driving software system to execute the upper-level decision-making plan and transmit it to the canbus (Controller Area Network Bus, serial bus system) module through optimization for final execution.
  • the control module is directly related to the precision and somatosensory of the self-driving vehicle.
  • Embodiments of the present disclosure provide a control method, device, device, and storage medium for an automatic driving vehicle.
  • an embodiment of the present disclosure proposes a control method for an automatic driving vehicle, including: acquiring the real-time pitch angle of the vehicle; acquiring a predicted pitch angle corresponding to the real-time pitch angle; determining the vehicle's pitch angle based on the real-time pitch angle and the predicted pitch angle Acceleration; control vehicle travel based on acceleration.
  • the embodiment of the present disclosure proposes a control device for an automatic driving vehicle, including: a first acquisition module configured to acquire the real-time pitch angle of the vehicle; a second acquisition module configured to acquire the corresponding real-time pitch angle The predicted pitch angle; the determination module is configured to determine the acceleration of the vehicle based on the real-time pitch angle and the predicted pitch angle; the control module is configured to control the driving of the vehicle based on the acceleration.
  • an embodiment of the present disclosure provides an electronic device, including: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by Executed by at least one processor, so that at least one processor can execute the method described in any implementation manner of the first aspect.
  • the embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions, the computer instructions are used to make a computer execute the method described in any implementation manner in the first aspect.
  • the embodiments of the present disclosure provide a computer program product, including a computer program.
  • the computer program When the computer program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.
  • FIG. 1 is an exemplary system architecture diagram in which the present disclosure can be applied
  • FIG. 2 is a flowchart of an embodiment of a control method of an autonomous vehicle according to the present disclosure
  • FIG. 3 is a flowchart of another embodiment of a control method of an autonomous vehicle according to the present disclosure
  • FIG. 4 is a flow chart of another embodiment of a control method for an autonomous vehicle according to the present disclosure.
  • Fig. 5 is a flow chart of another embodiment of the control method of the self-driving vehicle according to the present disclosure.
  • FIG. 6 is a schematic structural diagram of an embodiment of a control device for an autonomous vehicle according to the present disclosure.
  • FIG. 7 is a block diagram of an electronic device for implementing the control method of an automatic driving vehicle according to an embodiment of the present disclosure.
  • FIG. 1 shows an exemplary system architecture 100 to which embodiments of the control method for an automatic driving vehicle or the control device for an automatic driving vehicle of the present disclosure can be applied.
  • a system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 .
  • the network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 .
  • Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.
  • terminal devices 101, 102, 103 Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send action information and the like.
  • Various client applications may be installed on the terminal devices 101 , 102 , 103 , such as shooting applications and the like.
  • the terminal devices 101, 102, and 103 may be hardware or software.
  • the terminal devices 101, 102, 103 When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers and the like.
  • the terminal devices 101, 102, and 103 are software, they can be installed in the above-mentioned electronic devices. It can be implemented as a plurality of software or software modules, or as a single software or software module. No specific limitation is made here.
  • the server 105 can provide various services.
  • the server 105 may analyze and process the pitch angles obtained from the terminal devices 101, 102, 103, and generate processing results (such as acceleration, etc.).
  • the server 105 may be hardware or software.
  • the server 105 can be implemented as a distributed server cluster composed of multiple servers, or as a single server.
  • the server 105 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module. No specific limitation is made here.
  • control method of the self-driving vehicle is generally executed by the server 105 , and correspondingly, the control device of the self-driving vehicle is generally disposed in the server 105 .
  • terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.
  • FIG. 2 shows a flow 200 of an embodiment of a method for controlling an autonomous vehicle according to the present disclosure.
  • the control method of the self-driving vehicle includes the following steps:
  • Step 201 acquire the real-time pitch angle of the vehicle.
  • the execution subject of the control method of the autonomous vehicle can obtain the real-time pitch angle of the vehicle.
  • the pitch angle (that is, the pitch angle) may represent an inclination angle between the vehicle and the road surface, and the vehicle in this embodiment refers to an automatic driving vehicle.
  • the real-time pitch angle here can be collected by the vehicle attitude sensor.
  • the vehicle attitude sensor is usually a sensor of the self-driving vehicle, which can obtain the body attitude information of the self-driving vehicle, such as vehicle speed and angular velocity of the vehicle.
  • autonomous vehicles also known as unmanned vehicles, computer-driven vehicles, or wheeled mobile robots, are intelligent vehicles that realize unmanned driving through computer systems. It relies on artificial intelligence, visual computing, radar, surveillance devices and global positioning systems to work together to allow computers to automatically and safely operate motor vehicles without any active human operation.
  • Step 202 obtaining a predicted pitch angle corresponding to the real-time pitch angle.
  • the above-mentioned execution subject can obtain the predicted pitch angle corresponding to the real-time pitch angle, wherein the predicted pitch angle is the pitch angle of the predicted point output in the MPC (Model Predictive Control, Model Predictive Control) of the autonomous vehicle .
  • MPC Model Predictive Control, Model Predictive Control
  • the real-time pitch angle of the vehicle at the current position may be different from the predicted pitch angle. If the real-time pitch angle is different from the predicted pitch angle , the parameters of the current vehicle can be adjusted in time to achieve optimal control of the autonomous vehicle.
  • Step 203 determining the acceleration of the vehicle based on the real-time pitch angle and the predicted pitch angle.
  • the execution subject may determine the acceleration of the vehicle based on the real-time pitch angle and the predicted pitch angle.
  • the execution subject can determine the current road condition of the vehicle according to the real-time pitch angle and the predicted pitch angle of the vehicle. For example, if the vehicle continues to drive on a smooth road, the change in inclination between the vehicle and the road should be a constant value, while if the vehicle continues to drive on a bumpy road, the change in the inclination between the vehicle and the road will occur If the road has obvious unevenness and the uneven road section is long, the passengers in the self-driving vehicle will feel obvious bumps. Therefore, the above-mentioned execution subject will control the acceleration of the self-driving vehicle based on the real-time pitch angle and the predicted pitch angle, so as to optimize the automatic driving body feeling on bumpy road sections.
  • Step 204 controlling the vehicle to travel based on the acceleration.
  • the execution subject may control the driving of the autonomous vehicle based on the acceleration obtained in step 203 .
  • the execution subject may generate a driving instruction based on the acceleration to be adopted determined in step 203 and output the travel instruction.
  • the execution subject may directly output the travel instruction including the acceleration to be adopted.
  • the control method of the self-driving vehicle provided by the embodiment of the present disclosure first obtains the real-time pitch angle of the vehicle; then obtains the predicted pitch angle corresponding to the real-time pitch angle; then determines the acceleration of the vehicle based on the real-time pitch angle and the predicted pitch angle; finally, based on the acceleration Control the driving of the vehicle.
  • the present disclosure provides a control method of an automatic driving vehicle, which can determine the acceleration of the current vehicle based on the real-time pitch angle and the predicted pitch angle of the current position, and control the driving of the vehicle based on the acceleration, thereby optimizing the driving speed of the automatic driving vehicle. Automatic driving control accuracy and somatosensory on bumpy roads.
  • FIG. 3 shows a flow 300 of another embodiment of the method for controlling an autonomous vehicle according to the present disclosure.
  • the control method of the self-driving vehicle includes the following steps:
  • Step 301 acquiring the real-time pitch angle of the vehicle.
  • Step 302 obtaining a predicted pitch angle corresponding to the real-time pitch angle.
  • the above-mentioned predicted pitch angle is obtained through the following steps: obtaining the current location information of the vehicle; matching the current location information with the pre-built map coordinate points; and determining the predicted pitch angle based on the matching result.
  • the acquisition method of the current location information of the vehicle can be realized by using related technologies, which will not be repeated here.
  • the map here refers to a high-precision map, which refers to a machine-oriented high-precision map for self-driving cars.
  • the absolute precision is generally at the sub-meter level, that is, the precision within 1 meter, such as within 20 centimeters, and the horizontal relative Accuracy (eg, lane-to-lane, lane-to-lane line relative positional accuracy) tends to be even higher.
  • high-precision maps not only have high-precision coordinates, but also accurate road shapes, and contain data on the slope, curvature, heading, elevation, and roll of each lane.
  • high-precision maps need to have the ability to assist in achieving high-precision positioning, have road-level and lane-level planning capabilities, and have lane-level guidance capabilities.
  • ⁇ is the predicted pitch angle
  • ⁇ x is x 1 -x 2
  • ⁇ y is y 1 -y 2
  • ⁇ z is z 1 -z 2 .
  • Step 303 determining the acceleration of the vehicle based on the real-time pitch angle and the predicted pitch angle.
  • Steps 301-303 are basically the same as steps 201-203 in the foregoing embodiments, and the specific implementation manner may refer to the foregoing description of steps 201-203, which will not be repeated here.
  • Step 304 acquiring the current mass of the vehicle.
  • the execution subject of the method for controlling an autonomous vehicle can obtain the current quality of the vehicle.
  • the self-driving vehicle is a self-driving bus
  • the current quality of the self-driving vehicle can be collected through the load sensor installed on the self-driving vehicle.
  • step 304 includes: acquiring driving parameter information of the vehicle; and calculating the current mass of the vehicle based on the real-time pitch angle and driving parameter information. Since not all self-driving vehicles are equipped with load sensors, the driving parameter information of the vehicle can be obtained when the load sensor is not installed on the self-driving vehicle.
  • the driving parameter information includes: wheel torque, tire rotation radius, tire side Partial stiffness, air resistance, vehicle speed, etc., and then calculate the current mass of the vehicle through the formula (2), the formula (2) is as follows:
  • m is the current mass of the vehicle
  • T is the wheel torque
  • r is the radius of rotation of the tire
  • Fair is the air resistance
  • c r is the cornering stiffness of the tire
  • ⁇ 1 is the real-time pitch angle
  • g is the acceleration of gravity.
  • the pitch angle of the current position point is generally obtained directly from the imu (Inertial Measurement Unit, inertial measurement unit) sensor, and the pitch angle is considered to be a constant value in the preview window.
  • the pitch angle of the time-varying road is obtained, and the current mass of the vehicle is calculated through the formula (2) based on the obtained pitch angle, so as to achieve control adaptation of the automatic driving vehicle on a bumpy road.
  • step 304 may be executed during the execution of steps 301-303, or may be executed before step 301, or may be executed with Any step in steps 301-303 is executed simultaneously.
  • Step 305 correcting the acceleration based on the current mass to obtain the corrected acceleration.
  • the execution subject may correct the acceleration based on the current mass to obtain the corrected acceleration.
  • the corresponding accelerations should be different, so that the body feeling of the vehicle can be optimized. Therefore, in this embodiment, the acceleration obtained in step 303 is corrected based on the current mass of the vehicle obtained in step 304. , so as to get the corrected acceleration, that is, the corrected acceleration.
  • Step 306 controlling the vehicle to travel based on the corrected acceleration.
  • the execution subject may control the vehicle to travel based on the corrected acceleration.
  • the execution subject may generate a driving instruction based on the determined correction acceleration to be adopted and output the driving instruction.
  • the control method of the self-driving vehicle in this embodiment can correct the obtained acceleration based on the current mass of the self-driving vehicle to obtain the corrected acceleration, and The driving of the vehicle is controlled based on the corrected acceleration, so as to optimize the control accuracy and body feeling of autonomous vehicles of different qualities.
  • FIG. 4 shows a flow 400 of another embodiment of a control method for an autonomous vehicle according to the present disclosure.
  • the control method of the self-driving vehicle includes the following steps:
  • Step 401 acquire the real-time pitch angle of the vehicle.
  • Step 402 obtaining a predicted pitch angle corresponding to the real-time pitch angle.
  • Step 403 determining the acceleration of the vehicle based on the real-time pitch angle and the predicted pitch angle.
  • Step 404 acquiring the current mass of the vehicle.
  • Steps 401-404 are basically the same as steps 301-304 in the foregoing embodiments, and the specific implementation manner may refer to the foregoing description of steps 301-304, which will not be repeated here.
  • Step 405 matching the current quality with the preset quality range to obtain quality parameters.
  • the executing subject of the control method of the automatic driving vehicle can match the current quality of the automatic driving vehicle with a preset quality range to obtain quality parameters.
  • three corresponding preset values can be set in advance: no-load, medium-load, and heavy-load. is m light ; the medium load means that the passengers currently carried by the vehicle are about half of the number of passengers loaded by the vehicle, and the mass of the medium load of the vehicle is set as m mid ; the heavy load means that the passengers currently carried by the vehicle are almost half of the number of passengers loaded by the vehicle state, set the mass of the vehicle's heavy load to m full .
  • the current quality of the vehicle obtained in step 404 is matched with the three preset quality preset values, so as to determine the quality parameter corresponding to the current quality.
  • Step 406 Correct the acceleration according to the quality parameter and the preset correction parameter to obtain the corrected acceleration.
  • the execution subject may correct the acceleration according to the quality parameter obtained in step 405 and the preset correction parameter to obtain the corrected acceleration.
  • a corresponding correction parameter can be set for each mass preset value, so that when the mass of the vehicle is different, the current acceleration can be corrected based on the correction parameter corresponding to the current mass, from to correct the acceleration, so as to target different masses The acceleration of the vehicle is corrected to achieve a better body feeling.
  • Step 407 controlling the vehicle to travel based on the corrected acceleration.
  • Step 407 is basically the same as step 306 in the foregoing embodiment, and for a specific implementation manner, reference may be made to the foregoing description of step 306 , which will not be repeated here.
  • the control method of the self-driving vehicle in this embodiment first matches the current quality of the self-driving vehicle with the preset quality range to obtain the quality parameter; Then, according to the quality parameter and the corresponding correction parameter, the acceleration is corrected to obtain the corrected acceleration.
  • the method can more accurately correct the acceleration of the self-driving vehicle under different masses, so that the self-driving vehicle can be controlled with the corrected and optimal acceleration, thereby achieving a better body feeling.
  • FIG. 5 shows a flow 500 of still another embodiment of the control method of an autonomous vehicle according to the present disclosure.
  • the control method of the self-driving vehicle includes the following steps:
  • Step 501 acquire the real-time pitch angle of the vehicle.
  • Step 502 obtaining a predicted pitch angle corresponding to the real-time pitch angle.
  • Step 503 determining the acceleration of the vehicle based on the real-time pitch angle and the predicted pitch angle.
  • Step 504 acquiring the current quality of the vehicle.
  • Step 505 matching the current quality with the preset quality range to obtain quality parameters.
  • Steps 501-505 are basically the same as steps 401-405 in the foregoing embodiments, and the specific implementation manner may refer to the foregoing description of steps 401-405, which will not be repeated here.
  • Step 506 determine the driving state of the vehicle.
  • the executing body of the control method for an autonomous vehicle can determine the driving state of the vehicle, where the driving state includes a starting state or a parking state.
  • the current acceleration and speed of the vehicle can also be obtained, and then it can be judged whether the current acceleration, current speed, planned acceleration, and planned speed of the vehicle are within the preset threshold range in the starting state , if it is, the vehicle is in the starting state.
  • the vehicle is in the parking state.
  • the acceleration of vehicles in different driving states can be adjusted.
  • step 507-508 If the driving state of the vehicle is the starting state, then execute steps 507-508, and if the driving state of the vehicle is the parking state, then directly execute step 509.
  • Step 507 according to the quality parameter and the corresponding preset acceleration attenuation value, calculate the acceleration attenuation value of the vehicle under the current mass.
  • the above-mentioned executive body can calculate the acceleration attenuation value of the vehicle under the current mass according to the quality parameter and the corresponding preset acceleration attenuation value, wherein the acceleration attenuation value is used to prevent the occurrence of sudden acceleration and rapid acceleration .
  • the corresponding acceleration decay value (decay) can be set for each quality preset value, the acceleration decay value corresponding to m light is decay light , the acceleration decay value corresponding to m mid is decay mid , and the acceleration decay value corresponding to m full is decay full , through the determined quality parameters of the current quality and the above-mentioned preset acceleration attenuation value, the decay corresponding to the current ride quality m is found by the first-order linear difference method.
  • Step 508 correct the acceleration according to the acceleration attenuation value, and calculate the corrected acceleration, that is, the starting acceleration.
  • the execution subject may correct the acceleration based on the acceleration attenuation value obtained in step 507, so as to obtain the corrected acceleration, that is, the starting acceleration.
  • the model predictive controller can calculate and output the current optimal acceleration acc and the warm-up acceleration compensation value acc warmup , acc warmup is used to overcome static friction and prevent the vehicle from being unable to move forward. Based on formula (5), it can be Calculate the starting acceleration acc output , the formula (5) is as follows:
  • the acceleration attenuation value of the vehicle under the current mass can be calculated based on the quality parameter and the corresponding acceleration attenuation value, and the acceleration can be corrected according to the acceleration attenuation value, so as to obtain the starting acceleration, so as to prevent rapid acceleration at the starting stage, The emergence of rapid acceleration, thereby improving the somatosensory experience of self-driving vehicles.
  • Step 509 according to the quality parameter and the corresponding preset acceleration rate of change, the acceleration is corrected to obtain the corrected acceleration, that is, the parking acceleration.
  • the execution subject may correct the acceleration according to the quality parameter and the corresponding preset acceleration rate of change to obtain the corrected acceleration, that is, the parking acceleration, so as to make corresponding adjustments to the acceleration of the vehicle in the parked state.
  • the corresponding jerk rate can be preset for each quality preset value, and then the acceleration is corrected based on the jerk rate corresponding to the quality parameter, so as to obtain the parking acceleration.
  • a corresponding acceleration change rate acc_change_rate
  • acc_change_rate can be set for each quality preset value, and then the acc_change_rate corresponding to the quality parameter of the current quality can be determined, and the acc_change_rate can be used to control the acceleration of the vehicle.
  • step 509 includes: obtaining the current speed of the vehicle; obtaining a corresponding preset acceleration value based on the current speed; according to the quality parameter, the corresponding preset acceleration rate of change, and the preset acceleration value, Determine the parking acceleration.
  • the current speed of the vehicle can be obtained, and it can be judged whether the current speed satisfies the preset condition. If so, the acceleration is set to the corresponding preset acceleration value, and then based on the quality parameter, the corresponding preset acceleration rate of change and the preset acceleration value to determine the parking acceleration.
  • soft_brake_acc soft brake acceleration value
  • the complete stop speed (complete_stop_speed) can be set in advance, and then the current speed of the self-driving vehicle can be obtained to determine whether the current speed is lower than complete_stop_speed. If it is lower, it means that the self-driving vehicle has entered the final stage before braking. , then the acceleration is set to the preset acceleration before braking, and then the parking acceleration is determined based on the quality parameter, the corresponding preset acceleration rate of change, and the acceleration before braking.
  • Step 510 control the vehicle to travel based on the corrected acceleration.
  • Step 510 is basically the same as step 407 of the foregoing embodiment, and for a specific implementation manner, reference may be made to the foregoing description of step 407, and details are not repeated here.
  • control method of the self-driving vehicle in this embodiment can control the acceleration of the self-driving vehicle in different driving states to
  • the control parameters are adaptive to the quality, so as to improve the control accuracy and body feeling of the automatic driving vehicle in the scene of entering and exiting the station.
  • the present disclosure provides an embodiment of a control device for an automatic driving vehicle, which corresponds to the method embodiment shown in FIG. 2 .
  • the device can be specifically applied to various electronic devices.
  • the control device 600 for an autonomous vehicle in this embodiment may include: a first acquisition module 601 , a second acquisition module 602 , a determination module 603 and a control module 604 .
  • the first obtaining module 601 is configured to obtain the real-time pitch angle of the vehicle
  • the second obtaining module 602 is configured to obtain the predicted pitch angle corresponding to the real-time pitch angle
  • the determination module 603 is configured to obtain the real-time pitch angle and The acceleration of the vehicle is determined by predicting the pitch angle
  • the control module 604 is configured to control the driving of the vehicle based on the acceleration.
  • the specific processing of the first acquisition module 601, the second acquisition module 602, the determination module 603 and the control module 604 and the technical effects brought by them can refer to FIG. 2 respectively. Relevant descriptions corresponding to steps 201-204 in the embodiment are not repeated here.
  • control module includes: an acquisition submodule configured to acquire the current mass of the vehicle; a correction submodule configured to correct the acceleration based on the current mass to obtain a corrected acceleration; control A submodule configured to control the vehicle to travel based on the modified acceleration.
  • the acquisition submodule includes: an acquisition unit configured to acquire driving parameter information of the vehicle; a calculation unit configured to calculate and obtain the driving parameter information of the vehicle based on the real-time pitch angle and driving parameter information. current quality.
  • the correction submodule includes: a matching unit configured to match the current quality with a preset quality range to obtain a quality parameter; a correction unit configured to match the current quality with a preset quality range; The preset correction parameters are used to correct the acceleration to obtain the corrected acceleration.
  • the corrected acceleration when the vehicle is in the starting state, the corrected acceleration includes the starting acceleration, and the correcting unit includes: a first calculation subunit configured to The attenuation value is calculated to obtain the acceleration attenuation value of the vehicle under the current mass; the second calculation subunit is configured to correct the acceleration according to the acceleration attenuation value to calculate the starting acceleration.
  • the corrected acceleration when the vehicle is in a parked state, the corrected acceleration includes parking acceleration, and the correcting unit includes: a correcting subunit configured to , correct the acceleration to obtain the parking acceleration.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • FIG. 7 shows a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure.
  • Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 700 includes a computing unit 701 that can execute according to a computer program stored in a read-only memory (ROM) 702 or loaded from a storage unit 708 into a random-access memory (RAM) 703. Various appropriate actions and treatments. In the RAM 703, various programs and data necessary for the operation of the device 700 can also be stored.
  • the computing unit 701, ROM 702, and RAM 703 are connected to each other through a bus 704.
  • An input/output (I/O) interface 705 is also connected to the bus 704 .
  • the I/O interface 705 includes: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc. ; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 709 allows the device 700 to exchange information/data with other devices over a computer network such as the Internet and/or various telecommunication networks.
  • the computing unit 701 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of computing units 701 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the computing unit 701 executes various methods and processes described above, such as a control method of an autonomous vehicle.
  • the method of controlling an autonomous vehicle may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708 .
  • part or all of the computer program may be loaded and/or installed on the device 700 via the ROM 702 and/or the communication unit 709.
  • the computer program When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the control method of the self-driving vehicle described above can be executed.
  • the computing unit 701 may be configured in any other appropriate way (for example, by means of firmware) to execute a control method for an automatic driving vehicle.
  • Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC system of systems
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • programmable processor can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the management difficulties in traditional physical host and virtual private server (VPS, Virtual Private Server) services Large and weak business expansion.
  • cloud server also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the management difficulties in traditional physical host and virtual private server (VPS, Virtual Private Server) services Large and weak business expansion.
  • VPN Virtual Private Server
  • steps may be reordered, added or deleted using the various forms of flow shown above.
  • each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

Abstract

本公开公开了一种自动驾驶车辆的控制方法、装置、设备以及存储介质，涉及人工智能技术领域，具体为自动驾驶和智能交通领域。该方法的一具体实施方式包括：获取车辆的实时俯仰角度；获取与实时俯仰角度对应的预测俯仰角度；基于实时俯仰角度和预测俯仰角度确定车辆的加速度；基于加速度控制车辆行驶。该实施方式节省了对自动驾驶车辆的调优时间，并提升了自动驾驶车辆的体感。

Description

自动驾驶车辆的控制方法、装置、设备以及存储介质
本专利申请要求于2021年05月28日提交的、申请号为202110591412.7、发明名称为“自动驾驶车辆的控制方法、装置、设备以及存储介质”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本公开实施例涉及计算机领域，具体涉及自动驾驶和智能交通等人工智能技术领域，尤其涉及自动驾驶车辆的控制方法、装置、设备以及存储介质。
背景技术
自动驾驶车辆可以依靠人工智能、视觉计算、雷达、监控装置等协同合作，让车载的电脑可以在没有任何人类操作的情况下，自动安全地控制自动驾驶车辆。在自动驾驶车辆体系中，控制模块是自动驾驶软件系统执行上层决策规划，并通过优化传送至canbus(Controller Area Network Bus，串行总线系统)模块最终执行的重要模块。控制模块直接关系着自动驾驶车辆的精度和体感。
发明内容
本公开实施例提出了一种自动驾驶车辆的控制方法、装置、设备以及存储介质。
第一方面，本公开实施例提出了一种自动驾驶车辆的控制方法，包括：获取车辆的实时俯仰角度；获取与实时俯仰角度对应的预测俯仰角度；基于实时俯仰角度和预测俯仰角度确定车辆的加速度；基于加速度控制车辆行驶。
第二方面，本公开实施例提出了一种自动驾驶车辆的控制装置， 包括：第一获取模块，被配置成获取车辆的实时俯仰角度；第二获取模块，被配置成获取与实时俯仰角度对应的预测俯仰角度；确定模块，被配置成基于实时俯仰角度和预测俯仰角度确定车辆的加速度；控制模块，被配置成基于加速度控制车辆行驶。
第三方面，本公开实施例提出了一种电子设备，包括：至少一个处理器；以及与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行如第一方面中任一实现方式描述的方法。
第四方面，本公开实施例提出了一种存储有计算机指令的非瞬时计算机可读存储介质，计算机指令用于使计算机执行如第一方面中任一实现方式描述的方法。
第五方面，本公开实施例提出了一种计算机程序产品，包括计算机程序，计算机程序在被处理器执行时实现如第一方面中任一实现方式描述的方法。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本公开的其它特征、目的和优点将会变得更明显。附图用于更好地理解本方案，不构成对本公开的限定。其中：
图1是本公开可以应用于其中的示例性系统架构图；
图2是根据本公开的自动驾驶车辆的控制方法的一个实施例的流程图；
图3是根据本公开的自动驾驶车辆的控制方法的另一个实施例的流程图；
图4是根据本公开的自动驾驶车辆的控制方法的又一个实施例的流程图；
图5是根据本公开的自动驾驶车辆的控制方法的再一个实施例的 流程图；
图6是根据本公开的自动驾驶车辆的控制装置的一个实施例的结构示意图；
图7是用来实现本公开实施例的自动驾驶车辆的控制方法的电子设备的框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
需要说明的是，在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本公开。
图1示出了可以应用本公开的自动驾驶车辆的控制方法或自动驾驶车辆的控制装置的实施例的示例性系统架构100。
如图1所示，系统架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
用户可以使用终端设备101、102、103通过网络104与服务器105交互，以接收或发送动作信息等。终端设备101、102、103上可以安装有各种客户端应用，例如拍摄应用等等。
终端设备101、102、103可以是硬件，也可以是软件。当终端设备101、102、103为硬件时，可以是各种电子设备，包括但不限于智能手机、平板电脑、膝上型便携计算机和台式计算机等等。当终端设备101、102、103为软件时，可以安装在上述电子设备中。其可以实现成多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
服务器105可以提供各种服务。例如，服务器105可以对从终端设备101、102、103获取到的俯仰角度进行分析和处理，并生成处理结果(例如加速度等)。
需要说明的是，服务器105可以是硬件，也可以是软件。当服务器105为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器105为软件时，可以实现成多个软件或软件模块(例如用来提供分布式服务)，也可以实现成单个软件或软件模块。在此不做具体限定。
需要说明的是，本公开实施例所提供的自动驾驶车辆的控制方法一般由服务器105执行，相应地，自动驾驶车辆的控制装置一般设置于服务器105中。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。
继续参考图2，其示出了根据本公开的自动驾驶车辆的控制方法的一个实施例的流程200。该自动驾驶车辆的控制方法包括以下步骤：
步骤201，获取车辆的实时俯仰角度。
在本实施例中，自动驾驶车辆的控制方法的执行主体(例如图1所示的服务器105)可以获取车辆的实时俯仰角度。其中，俯仰角度(也即pitch角)可以表征车辆与路面之间的倾角，本实施例中的车辆指的是自动驾驶车辆。这里的实时俯仰角度可由车辆姿态传感器采集得到，其中，车辆姿态传感器通常为自动驾驶车辆自带的传感器，可以获取自动驾驶车辆的车身姿态信息，例如车速、车的角速度等。
需要说明的是，自动驾驶汽车(Autonomous vehicles)又称无人驾驶汽车、电脑驾驶汽车、或轮式移动机器人，是一种通过电脑系统实现无人驾驶的智能汽车。其依靠人工智能、视觉计算、雷达、监控装置和全球定位系统协同合作，让电脑可以在没有任何人类主动的操作下，自动安全地操作机动车辆。
步骤202，获取与实时俯仰角度对应的预测俯仰角度。
在本实施例中，上述执行主体可以获取与实时俯仰角度对应的预 测俯仰角度，其中，预测俯仰角度即为自动驾驶车辆的MPC(Model Predictive Control，模型预测控制)中输出的预测点的俯仰角度。
需要说明的是，由于在步骤201中已经获取了车辆在当前位置的实时俯仰角度，但是同一个位置的实时俯仰角度可能与预测俯仰角度是不同的，实时俯仰角度与预测俯仰角度不同的情况下，可以及时调整当前车辆的参数，以实现对自动驾驶车辆的最优控制。
步骤203，基于实时俯仰角度和预测俯仰角度确定车辆的加速度。
在本实施例中，上述执行主体可以基于实时俯仰角度和预测俯仰角度确定车辆的加速度。如步骤202所说，上述执行主体可以根据车辆的实时俯仰角度和预测俯仰角度，可以确定车辆当前所处的路况。例如，若车辆持续在平稳路段上行驶，车辆与路面之间的倾角的变化量应当为恒定值，而若车辆持续在颠簸路段上行驶，则车辆与路面之间的倾角的变化量就会发生变化，如果道路有明显的不平整且不平整路段较长，在自动驾驶车辆中乘坐的人员会感受到明显的颠簸。所以，上述执行主体会基于实时俯仰角度和预测俯仰角度来对自动驾驶车辆的加速度进行控制，以优化在颠簸路段的自动驾驶体感。
步骤204，基于加速度控制车辆行驶。
在本实施例中，上述执行主体可以基于步骤203得到的加速度控制自动驾驶车辆行驶。例如，上述执行主体可以基于步骤203所确定的将要采用的加速度，生成行驶指令并输出该行驶指令，如上述执行主体可以直接输出包括将要采用的加速度的行驶指令。
本公开实施例提供的自动驾驶车辆的控制方法，首先获取车辆的实时俯仰角度；之后获取与实时俯仰角度对应的预测俯仰角度；然后基于实时俯仰角度和预测俯仰角度确定车辆的加速度；最后基于加速度控制车辆行驶。本公开提供了一种自动驾驶车辆的控制方法，该方法能够基于当前位置的实时俯仰角度和预测俯仰角度来确定当前车辆的加速度，并基于该加速度来控制车辆行驶，从而优化了自动驾驶车辆在颠簸路段的自动驾驶控制精度和体感。
继续参考图3，图3示出了根据本公开的自动驾驶车辆的控制方 法的另一个实施例的流程300。该自动驾驶车辆的控制方法包括以下步骤：
步骤301，获取车辆的实时俯仰角度。
步骤302，获取与实时俯仰角度对应的预测俯仰角度。
在本实施例的一些可选实施方式中，上述预测俯仰角度通过以下步骤得到：获取车辆的当前位置信息；将当前位置信息与预先构建的地图坐标点进行匹配；基于匹配结果确定预测俯仰角度。其中，车辆的当前位置信息的获取方式可采用相关技术实现，这里不再赘述。
这里的地图是指高精度地图，是指面向机器的供自动驾驶汽车使用的高精度地图，绝对精度一般都会在亚米级，也就是1米以内的精度，例如20厘米以内，而且横向的相对精度(比如，车道和车道、车道和车道线的相对位置精度)往往还要更高。并且高精度地图不仅有高精度的坐标，同时还有准确的道路形状，并且含有每个车道的坡度、曲率、航向、高程以及侧倾的数据。同时，高精度地图需要具备辅助完成实现高精度的定位位置功能，具备道路级别和车道级别的规划能力，以及具备车道级别的引导能力。
在这里，将获取的车辆的当前位置信息与高精度地图中的坐标点进行匹配，假设当前点的坐标为(x 1，y 1，z 1)，高精度地图中的匹配点的坐标为(x 2，y 2，z 2)，从而确定高精度地图中相匹配点的坐标，然后通过公式(1)计算得到预测俯仰角度，公式(1)如下所示：
Figure PCTCN2021135073-appb-000001
其中，θ即为预测俯仰角度，Δx为x 1-x 2，Δy为y 1-y 2，Δz为z 1-z 2。
步骤303，基于实时俯仰角度和预测俯仰角度确定车辆的加速度。
步骤301-303与前述实施例的步骤201-203基本一致，具体实现方式可以参考前述对步骤201-203的描述，此处不再赘述。
步骤304，获取车辆的当前质量。
在本实施例中，自动驾驶车辆的控制方法的执行主体(例如图1所示的服务器105)可以获取车辆的当前质量。当自动驾驶车辆为自动驾驶巴士车时，在该自动驾驶巴士车的行驶过程中，由于乘坐人员的 不确定性(如到站上、下车)，会导致自动驾驶车辆的整车质量有较大的波动，所以，本实施例中需要实时获取自动驾驶车辆的当前质量。其中，可通过安装在自动驾驶车辆上的载重传感器采集车辆的当前质量。
在本实施例的一些可选实施方式中，步骤304包括：获取车辆的行驶参数信息；基于实时俯仰角度和行驶参数信息，计算得到车辆的当前质量。由于不是所有的自动驾驶车辆上都会安装有载重传感器，在自动驾驶车辆上没有安装载重传感器的情况下，可以获取车辆的行驶参数信息，行驶参数信息包括：轮边扭矩、轮胎转动半径、轮胎侧偏刚度、空气阻力以及车速等，然后通过公式(2)计算得到车辆的当前质量，公式(2)如下所示：
Figure PCTCN2021135073-appb-000002
其中，m为车辆的当前质量，T为轮边扭矩，r为轮胎转动半径，F air为空气阻力，c r为轮胎侧偏刚度，
Figure PCTCN2021135073-appb-000003
为车辆的速度，θ 1为实时俯仰角度，g为重力加速度。
由于相关方案中，一般会从imu(Inertial Measurement Unit，惯性测量单元)传感器直接获取的当前位置点的pitch角，并在预瞄窗口内认为pitch角为常值。而在较为颠簸的路段，将pitch角仍认为是常值是不合理的。所以，本实施例中通过获取时变道路的pitch角，并将基于获取的pitch角来通过公式(2)来计算车辆的当前质量，从而达到自动驾驶车辆在颠簸路面下的控制自适应。
需要说明的是，本公开对步骤304与步骤301-303的执行顺序不做具体限定，也即步骤304可在步骤301-303的执行过程中执行，也可以在步骤301之前执行，还可以与步骤301-303中的任意步骤同时执行。
步骤305，基于当前质量对加速度进行修正，得到修正加速度。
在本实施例中，上述执行主体可以基于当前质量对加速度进行修正，得到修正加速度。对于不同质量的自动驾驶车辆，其所对应的加速度应该是不同的，这样才能车辆的体感进行优化，所以，本实施例中，基于步骤304得到的车辆的当前质量对步骤303得到的加速度进行修正，从而到修正后的加速度，即修正加速度。例如，可以为不同 质量设置对应的质量系数，当车辆当前质量对应的系数较大时，可以将当前加速度相对调节的大些，当车辆当前质量对应的系数较小时，可以将当前加速度调节的相对小一些，从而保证不同质量的自动驾驶车辆的体感。
步骤306，基于修正加速度控制车辆行驶。
在本实施例中，上述执行主体可以基于修正加速度控制车辆行驶。上述执行主体可以基于所确定的将要采用的修正加速度，生成行驶指令并输出该行驶指令。
从图3中可以看出，与图2对应的实施例相比，本实施例中的自动驾驶车辆的控制方法可以基于自动驾驶车辆的当前质量对得到的加速度进行修正，以得到修正加速度，并基于该修正加速度控制该车辆行驶，从而达到对不同质量的自动驾驶车辆的控制精度和体感进行优化。
继续参考图4，图4示出了根据本公开的自动驾驶车辆的控制方法的又一个实施例的流程400。该自动驾驶车辆的控制方法包括以下步骤：
步骤401，获取车辆的实时俯仰角度。
步骤402，获取与实时俯仰角度对应的预测俯仰角度。
步骤403，基于实时俯仰角度和预测俯仰角度确定车辆的加速度。
步骤404，获取车辆的当前质量。
步骤401-404与前述实施例的步骤301-304基本一致，具体实现方式可以参考前述对步骤301-304的描述，此处不再赘述。
步骤405，将当前质量与预设的质量范围进行匹配，得到质量参数。
在本实施例中，自动驾驶车辆的控制方法的执行主体(例如图1所示的服务器105)可以将自动驾驶车辆的当前质量与预设的质量范围进行匹配，得到质量参数。其中，对于车辆质量，可以预先设置对应的三个预设值：空载、中载、重载，空载即为车辆当前为空或者所载乘客很少的状态，将车辆空载的质量设为m light；中载即为车辆当前所载 乘客大约为车辆负荷乘客数的一半左右，将车辆中载的质量设为m mid；重载即为车辆当前所载乘客几乎为车辆负荷乘客数的状态，将车辆重载的质量设为m full。将步骤404获取的车辆的当前质量与预设的三个质量预设值进行匹配，从而确定当前质量对应的质量参数。
步骤406，根据质量参数与预设的修正参数，对加速度进行修正，得到修正加速度。
在本实施例中，上述执行主体可以根据步骤405得到的质量参数与预设的修正参数，对加速度进行修正，得到修正加速度。例如，可为每个质量预设值设置对应的修正参数，以使当车辆质量不同时，能够基于与当前质量对应的修正参数来对当前加速度进行修正，从到修正加速度，从而针对不同质量的车辆的加速度进行修正，进而达到更优的体感。
步骤407，基于修正加速度控制车辆行驶。
在本实施例中，上述执行主体可以基于修正加速度来控制车辆行驶。步骤407与前述实施例的步骤306基本一致，具体实现方式可以参考前述对步骤306的描述，此处不再赘述。
从图4中可以看出，与图3对应的实施例相比，本实施例中的自动驾驶车辆的控制方法先将自动驾驶车辆的当前质量与预设的质量范围进行匹配，得到质量参数；然后根据该质量参数与对应的修正参数，对加速度进行修正，从而得到修正加速度。该方法能够更精准地对不同质量下的自动驾驶车辆的加速度进行修正，从而以修正后的、最优加速度对该自动驾驶车辆进行控制，进而达到更优的体感。
继续参考图5，图5示出了根据本公开的自动驾驶车辆的控制方法的再一个实施例的流程500。该自动驾驶车辆的控制方法包括以下步骤：
步骤501，获取车辆的实时俯仰角度。
步骤502，获取与实时俯仰角度对应的预测俯仰角度。
步骤503，基于实时俯仰角度和预测俯仰角度确定车辆的加速度。
步骤504，获取车辆的当前质量。
步骤505，将当前质量与预设的质量范围进行匹配，得到质量参数。
步骤501-505与前述实施例的步骤401-405基本一致，具体实现方式可以参考前述对步骤401-405的描述，此处不再赘述。
步骤506，确定车辆的行驶状态。
在本实施例中，自动驾驶车辆的控制方法的执行主体(例如图1所示的服务器105)可以确定车辆的行驶状态，其中，行驶状态包括起步状态或停车状态。
由于通过MPC可输出车辆当前规划的加速度和速度，还可以获取车辆当前的加速度和速度，之后可通过判断车辆当前加速度、当前速度以及规划加速度、规划速度是否在起步状态下预设的阈值范围内，如果在，则该车辆为起步状态。
相应的，可通过判断车辆当前加速度、当前速度以及规划加速度、规划速度是否在停车状态下预设的阈值范围内，如果在，则该车辆为停车状态。本实施例中可以对不同行驶状态的车辆的加速度进行调整。
若车辆的行驶状态为起步状态，则执行步骤507-508，若车辆的行驶状态为停车状态，则直接执行步骤509。
步骤507，根据质量参数与对应的预设加速度衰减值，计算得到车辆在当前质量下的加速度衰减值。
在本实施例中，上述执行主体可以根据质量参数与对应的预设加速度衰减值，计算得到车辆在当前质量下的加速度衰减值，其中，加速度衰减值用来防止猛加速、急加速情况的出现。例如，可为每个质量预设值设置对应的加速度衰减值(decay)，m light对应的加速度衰减值为decay light，m mid对应的加速度衰减值为decay mid，m full对应的加速度衰减值为decay full，通过确定的当前质量的质量参数与上述预设加速度衰减值，通过一阶线性差值的方法找到当前乘车质量m对应的decay。
例如：m∈[m light，m mid]，则通过以下公式(3)和(4)可计算得m对应的decay。
Figure PCTCN2021135073-appb-000004
decay＝k*(m-m light)+decay light       (4)
通过计算可以得到当前质量m对应的加速度衰减值decay。
步骤508，根据加速度衰减值对加速度进行修正，计算得到修正加速度，即起步加速度。
在本实施例中，上述执行主体可以基于步骤507得到的加速度衰减值对加速度进行修正，从而得到修正后的加速度，也即起步加速度。在本实施例中，模型预测控制器可以计算输出当前的最优加速度acc，以及预热加速度补偿值acc warmup，acc warmup是用来克服静摩擦力的，防止车辆无法前进，基于公式(5)可以计算得到起步加速度acc output，公式(5)如下所示：
acc output＝decay*acc+acc warmup        (5)
通过上述步骤，可以基于质量参数与对应的加速度衰减值，计算得到车辆在当前质量下的加速度衰减值，并根据该加速度衰减值对加速度进行修正，从而得到起步加速度，以防止起步阶段猛加速、急加速情况的出现，进而提升自动驾驶车辆的体感。
步骤509，根据质量参数与对应的预设加速度变化率，对加速度进行修正，得到修正加速度，即停车加速度。
在本实施例中，上述执行主体可以根据质量参数与对应的预设加速度变化率，对加速度进行修正，得到修正加速度，即停车加速度，从而为停车状态的车辆的加速度进行相应调整。
在本实施例中，可以为每个质量预设值预先设置对应的加速度变化率，然后基于质量参数对应的加速度变化率对加速度进行修正，从而得到停车加速度。例如，可为每个质量预设值设置对应的加速度变化率(acc_change_rate)，再确定与当前质量的质量参数对应的acc_change_rate，并使用该acc_change_rate来控制车辆的加速度。
在本实施例的一些可选实施方式中，步骤509包括：获取车辆的当前速度；基于当前速度得到对应的预设加速度值；根据质量参数、对应的预设加速度变化率以及预设加速度值，确定停车加速度。例如，可获取车辆的当前速度，并判断当前速度是否满足预设条件，若满足，则将加速度设置为对应的预设加速度值，再基于质量参数、对应的预设加速度变化率以及预设加速度值，来确定停车加速度。
作为一个示例，可以预先设置轻刹车加速度值(soft_brake_acc)，然后获取自动驾驶车辆的当前速度，判断当前速度是否在预设的完全停止速度与预设的轻刹车速度之间，若在，则将加速度设置为的预设的soft_brake_acc，再基于质量参数、对应的预设加速度变化率以及soft_brake_acc，来确定停车加速度。
作为另一个示例，可以预先设置完全停止速度(complete_stop_speed)，然后获取自动驾驶车辆的当前速度，判断当前速度是否低于complete_stop_speed，若低于，则说明自动驾驶车辆已经进入到刹停前的最后阶段，那么将加速度设置为的预设的刹停前加速度，再基于质量参数、对应的预设加速度变化率以及刹停前加速度，来确定停车加速度。
步骤510，基于修正加速度控制车辆行驶。
在本实施例中，上述执行主体可以基于修正加速度来控制车辆行驶。步骤510与前述实施例的步骤407基本一致，具体实现方式可以参考前述对步骤407的描述，此处不再赘述。
从图5中可以看出，与图4对应的实施例相比，本实施例中的自动驾驶车辆的控制方法可以对不同行驶状态的自动驾驶车辆的加速度进行控制，以基于起步状态和停车状态的控制参数作相对于质量的自适应方案，从而提升自动驾驶车辆进站出站场景下的控制精度和体感。
进一步参考图6，作为对上述各图所示方法的实现，本公开提供了一种自动驾驶车辆的控制装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图6所示，本实施例的自动驾驶车辆的控制装置600可以包括：第一获取模块601、第二获取模块602、确定模块603和控制模块604。其中，第一获取模块601，被配置成获取车辆的实时俯仰角度；第二获取模块602，被配置成获取与实时俯仰角度对应的预测俯仰角度；确定模块603，被配置成基于实时俯仰角度和预测俯仰角度确定车辆的加速度；控制模块604，被配置成基于加速度控制车辆行驶。
在本实施例中，自动驾驶车辆的控制装置600中：第一获取模块 601、第二获取模块602、确定模块603和控制模块604的具体处理及其所带来的技术效果可分别参考图2对应实施例中的步骤201-204的相关说明，在此不再赘述。
在本实施例的一些可选的实现方式中，控制模块包括：获取子模块，被配置成获取车辆的当前质量；修正子模块，被配置成基于当前质量对加速度进行修正，得到修正加速度；控制子模块，被配置成基于修正加速度控制车辆行驶。
在本实施例的一些可选的实现方式中，获取子模块包括：获取单元，被配置成获取车辆的行驶参数信息；计算单元，被配置成基于实时俯仰角度和行驶参数信息，计算得到车辆的当前质量。
在本实施例的一些可选的实现方式中，修正子模块包括：匹配单元，被配置成将当前质量与预设的质量范围进行匹配，得到质量参数；修正单元，被配置成根据质量参数与预设的修正参数，对加速度进行修正，得到修正加速度。
在本实施例的一些可选的实现方式中，在车辆为起步状态的情况下，修正加速度包括起步加速度，修正单元包括：第一计算子单元，被配置成根据质量参数与对应的预设加速度衰减值，计算得到车辆在当前质量下的加速度衰减值；第二计算子单元，被配置成根据加速度衰减值对加速度进行修正，计算得到起步加速度。
在本实施例的一些可选的实现方式中，在车辆为停车状态的情况下，修正加速度包括停车加速度，修正单元包括：修正子单元，被配置成根据质量参数与对应的预设加速度变化率，对加速度进行修正，得到停车加速度。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
图7示出了可以用来实施本公开的实施例的示例电子设备700的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种 形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图7所示，设备700包括计算单元701，其可以根据存储在只读存储器(ROM)702中的计算机程序或者从存储单元708加载到随机访问存储器(RAM)703中的计算机程序，来执行各种适当的动作和处理。在RAM 703中，还可存储设备700操作所需的各种程序和数据。计算单元701、ROM 702以及RAM 703通过总线704彼此相连。输入/输出(I/O)接口705也连接至总线704。
设备700中的多个部件连接至I/O接口705，包括：输入单元706，例如键盘、鼠标等；输出单元707，例如各种类型的显示器、扬声器等；存储单元708，例如磁盘、光盘等；以及通信单元709，例如网卡、调制解调器、无线通信收发机等。通信单元709允许设备700通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
计算单元701可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元701的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元701执行上文所描述的各个方法和处理，例如自动驾驶车辆的控制方法。例如，在一些实施例中，自动驾驶车辆的控制方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元708。在一些实施例中，计算机程序的部分或者全部可以经由ROM 702和/或通信单元709而被载入和/或安装到设备700上。当计算机程序加载到RAM 703并由计算单元701执行时，可以执行上文描述的自动驾驶车辆的控制方法的一个或多个步骤。备选地，在其他实施例中，计算单元701可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行自动驾驶车辆的控制方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电 路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将 输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，又称为云计算服务器或云主机，是云计算服务体系中的一项主机产品，以解决传统物理主机与虚拟专用服务器(VPS，Virtual Private Server)服务中存在的管理难度大，业务扩展性弱的缺陷。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。

Claims (18)

  1. 自动驾驶车辆的控制方法，包括：
    获取车辆的实时俯仰角度；
    获取与所述实时俯仰角度对应的预测俯仰角度；
    基于所述实时俯仰角度和所述预测俯仰角度确定所述车辆的加速度；
    基于所述加速度控制所述车辆行驶。
  2. 根据权利要求1所述的方法，其中，所述基于所述加速度控制所述车辆行驶，包括：
    获取所述车辆的当前质量；
    基于所述当前质量对所述加速度进行修正，得到修正加速度；
    基于所述修正加速度控制所述车辆行驶。
  3. 根据权利要求2所述的方法，其中，所述获取所述车辆的当前质量，包括：
    获取所述车辆的行驶参数信息；
    基于所述实时俯仰角度和所述行驶参数信息，计算得到所述车辆的当前质量。
  4. 根据权利要求2所述的方法，其中，所述基于所述当前质量对所述加速度进行修正，得到修正加速度，包括：
    将所述当前质量与预设的质量范围进行匹配，得到质量参数；
    根据所述质量参数与预设的修正参数，对所述加速度进行修正，得到修正加速度。
  5. 根据权利要求4所述的方法，其中，所述方法还包括：
    确定所述车辆的行驶状态，其中，所述行驶状态包括起步状态或停车状态。
  6. 根据权利要求5所述的方法，其中，在所述车辆为起步状态的情况下，所述修正加速度包括起步加速度，所述根据所述质量参数与预设的修正参数，对所述加速度进行修正，得到修正加速度，包括：
    根据所述质量参数与对应的预设加速度衰减值，计算得到所述车辆在当前质量下的加速度衰减值；
    根据所述加速度衰减值对所述加速度进行修正，计算得到所述起步加速度。
  7. 根据权利要求5所述的方法，其中，在所述车辆为停车状态的情况下，所述修正加速度包括停车加速度，所述根据所述质量参数与预设的修正参数，对所述加速度进行修正，得到修正加速度，包括：
    根据所述质量参数与对应的预设加速度变化率，对所述加速度进行修正，得到所述停车加速度。
  8. 根据权利要求7所述的方法，其中，所述根据所述质量参数与对应的预设加速度变化率，对所述加速度进行修正，得到停车加速度，包括：
    获取所述车辆的当前速度；
    基于所述当前速度得到对应的预设加速度值；
    根据所述质量参数、对应的预设加速度变化率以及预设加速度值，确定所述停车加速度。
  9. 根据权利要求1-8中任一项所述的方法，其中，所述预测俯仰角度通过如下步骤得到：
    获取所述车辆的当前位置信息；
    将所述当前位置信息与预先构建的地图坐标点进行匹配；
    基于匹配结果确定所述预测俯仰角度。
  10. 自动驾驶车辆的控制装置，包括：
    第一获取模块，被配置成获取车辆的实时俯仰角度；
    第二获取模块，被配置成获取与所述实时俯仰角度对应的预测俯仰角度；
    确定模块，被配置成基于所述实时俯仰角度和所述预测俯仰角度确定所述车辆的加速度；
    控制模块，被配置成基于所述加速度控制所述车辆行驶。
  11. 根据权利要求10所述的装置，其中，所述控制模块包括：
    获取子模块，被配置成获取所述车辆的当前质量；
    修正子模块，被配置成基于所述当前质量对所述加速度进行修正，得到修正加速度；
    控制子模块，被配置成基于所述修正加速度控制所述车辆行驶。
  12. 根据权利要求11所述的装置，其中，所述获取子模块包括：
    获取单元，被配置成获取所述车辆的行驶参数信息；
    计算单元，被配置成基于所述实时俯仰角度和所述行驶参数信息，计算得到所述车辆的当前质量。
  13. 根据权利要求11所述的装置，其中，所述修正子模块包括：
    匹配单元，被配置成将所述当前质量与预设的质量范围进行匹配，得到质量参数；
    修正单元，被配置成根据所述质量参数与预设的修正参数，对所述加速度进行修正，得到修正加速度。
  14. 根据权利要求13所述的装置，其中，在所述车辆为起步状态的情况下，所述修正加速度包括起步加速度，所述修正单元包括：
    第一计算子单元，被配置成根据所述质量参数与对应的预设加速度衰减值，计算得到所述车辆在当前质量下的加速度衰减值；
    第二计算子单元，被配置成根据所述加速度衰减值对所述加速度进行修正，计算得到所述起步加速度。
  15. 根据权利要求13所述的装置，其中，在所述车辆为停车状态的情况下，所述修正加速度包括停车加速度，所述修正单元包括：
    修正子单元，被配置成根据所述质量参数与对应的预设加速度变化率，对所述加速度进行修正，得到所述停车加速度。
  16. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-9中任一项所述的方法。
  17. 一种存储有计算机指令的非瞬时计算机可读存储介质，所述计算机指令用于使所述计算机执行权利要求1-9中任一项所述的方法。
  18. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-9中任一项所述的方法。
PCT/CN2021/135073 2021-05-28 2021-12-02 自动驾驶车辆的控制方法、装置、设备以及存储介质 WO2022247203A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110591412.7A CN113183975B (zh) 2021-05-28 2021-05-28 自动驾驶车辆的控制方法、装置、设备以及存储介质
CN202110591412.7 2021-05-28

Publications (1)

Publication Number Publication Date
WO2022247203A1 true WO2022247203A1 (zh) 2022-12-01

Family

ID=76986377

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/135073 WO2022247203A1 (zh) 2021-05-28 2021-12-02 自动驾驶车辆的控制方法、装置、设备以及存储介质

Country Status (2)

Country Link
CN (1) CN113183975B (zh)
WO (1) WO2022247203A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113183975B (zh) * 2021-05-28 2022-04-05 阿波罗智能技术(北京)有限公司 自动驾驶车辆的控制方法、装置、设备以及存储介质
CN114274968A (zh) * 2021-11-09 2022-04-05 天津天瞳威势电子科技有限公司 一种车辆控制方法、装置、计算设备及存储介质
CN114194204A (zh) * 2021-11-30 2022-03-18 际络科技(上海)有限公司 自动驾驶车辆体感数据处理方法及系统
CN114684165B (zh) * 2022-03-04 2023-03-24 阿波罗智能技术(北京)有限公司 车辆控制方法、装置、设备、存储介质和自动驾驶车辆

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102016224464A1 (de) * 2015-12-14 2017-06-14 Hyundai Autron Co., Ltd. Vorrichtung zur Erfassung eines Fahrzeuglängsneigungswinkels unter Anwendung eines Beschleunigungssensors und eines Kreiselsensors und Verfahren dazu
CN110304065A (zh) * 2019-07-23 2019-10-08 广州小鹏汽车科技有限公司 一种车辆的起步控制方法、系统及车辆
CN112455446A (zh) * 2020-12-17 2021-03-09 北京航迹科技有限公司 用于车辆控制的方法、装置、电子设备和存储介质
CN113183975A (zh) * 2021-05-28 2021-07-30 阿波罗智能技术(北京)有限公司 自动驾驶车辆的控制方法、装置、设备以及存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6503585B2 (ja) * 2017-09-01 2019-04-24 本田技研工業株式会社 車両制御システム、車両制御方法、及びプログラム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102016224464A1 (de) * 2015-12-14 2017-06-14 Hyundai Autron Co., Ltd. Vorrichtung zur Erfassung eines Fahrzeuglängsneigungswinkels unter Anwendung eines Beschleunigungssensors und eines Kreiselsensors und Verfahren dazu
CN110304065A (zh) * 2019-07-23 2019-10-08 广州小鹏汽车科技有限公司 一种车辆的起步控制方法、系统及车辆
CN112455446A (zh) * 2020-12-17 2021-03-09 北京航迹科技有限公司 用于车辆控制的方法、装置、电子设备和存储介质
CN113183975A (zh) * 2021-05-28 2021-07-30 阿波罗智能技术(北京)有限公司 自动驾驶车辆的控制方法、装置、设备以及存储介质

Also Published As

Publication number Publication date
CN113183975A (zh) 2021-07-30
CN113183975B (zh) 2022-04-05

Similar Documents

Publication Publication Date Title
WO2022247203A1 (zh) 自动驾驶车辆的控制方法、装置、设备以及存储介质
US10488205B2 (en) Method and system for updating maps based on control feedbacks of autonomous driving vehicles
US11308391B2 (en) Offline combination of convolutional/deconvolutional and batch-norm layers of convolutional neural network models for autonomous driving vehicles
US11348339B2 (en) Association and tracking for autonomous devices
US10442435B2 (en) Speed control parameter estimation method for autonomous driving vehicles
JP7060625B2 (ja) 自動運転車において３ｄｃｎｎネットワークを用いてソリューション推断を行うｌｉｄａｒ測位
EP3315388B1 (en) Spring system-based change lane approach for autonomous vehicles
JP7256758B2 (ja) 自動運転車両においてｒｎｎとｌｓｔｍを用いて時間平滑化を行うｌｉｄａｒ測位
US9244462B2 (en) Vehicle trajectory planning for autonomous vehicles
EP3327464A1 (en) Algorithm and infrastructure for robust and efficient vehicle localization
US20190210591A1 (en) System and Method to Enhance the Driving Performance of a Leanable Vehicle
EP3327530B1 (en) Method for determining command delays of autonomous vehicles
WO2020237890A1 (zh) 一种速度规划方法、装置、电子设备及存储介质
US10272778B2 (en) Method and system for determining unit gain of speed control for autonomous driving vehicles
JP2021514885A (ja) 自動運転車のｌｉｄａｒ測位に用いられるディープラーニングに基づく特徴抽出方法
CN108891417A (zh) 用于操作自动驾驶车辆的方法及数据处理系统
US20180297606A1 (en) Automatic steering control reference adaption to resolve understeering of autonomous driving vehicles
WO2024051661A1 (zh) 路面不平度的分类识别方法、装置、车辆及存储介质
WO2024051188A1 (zh) 一种车辆行驶路面坡度预测方法、系统及其车辆
WO2023241556A1 (zh) 泊车控制方法、装置、设备和存储介质
CN115792985A (zh) 一种车辆定位方法、装置、电子设备、存储介质及车辆
WO2022105361A1 (zh) 车辆控制方法、装置、计算机可读存储介质及电子设备
CN114802250A (zh) 数据处理方法、装置、设备、自动驾驶车辆及介质
CN114771533A (zh) 自动驾驶车辆的控制方法、装置、设备、车辆及介质
CN110654458B (zh) 车辆方向盘控制方法、装置、计算机设备及车辆

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21942766

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE